{"id":"W3007557661","doi":"10.1109/icra40945.2020.9197562","title":"Self-Supervised Deep Pose Corrections for Robust Visual Odometry","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Visual odometry; Artificial intelligence; Odometry; Computer science; Ground truth; Estimator; Pose; Monocular; Computer vision; Supervised learning; Pattern recognition (psychology); Machine learning; Mathematics; Robot; Artificial neural network; Mobile robot","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000536304,0.001057164,0.0006680561,0.0005461671,0.0003163479,0.0005432558,0.001941712,0.0008290831,0.00227225],"category_scores_gemma":[0.002676524,0.000572698,0.0004450826,0.0006151056,0.0008353326,0.001181635,0.001657707,0.001497241,0.001189141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005628601,"about_ca_system_score_gemma":0.0009646597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004552715,"about_ca_topic_score_gemma":0.008631524,"domain_scores_codex":[0.9994647,0.00009047995,0.00001777952,0.0001811606,0.000189522,0.00005632464],"domain_scores_gemma":[0.9989968,0.0002011941,0.0001504196,0.0003456135,0.0002638547,0.00004208787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001425513,0.0001367667,0.00174095,0.000112312,0.00008292938,0.00007307437,0.0001052202,0.4256744,0.03007215,0.009025938,0.006446956,0.5263868],"study_design_scores_gemma":[0.000006191216,0.0000324944,0.0003443241,0.000007496546,0.000006469272,0.00003878636,0.000007673035,0.985142,0.008771021,0.00390245,0.001732499,0.000008544293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009614152,0.00008378945,0.9870684,0.0000543863,0.00004320612,0.00001689541,0.00007158052,0.002219991,0.000827683],"genre_scores_gemma":[0.6004612,0.0001720553,0.3923653,0.000223919,0.00008365303,0.0001100124,0.0007629363,0.0004693906,0.005351447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004552715,"threshold_uncertainty_score":0.009052455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530821469046263,"score_gpt":0.2421166221894535,"score_spread":0.2168084074989909,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}